# GPT-5 vs Mistral Large 3

> Side-by-side benchmark comparison for GPT-5 and Mistral Large 3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-vs-mistral-large-3
- Last updated: November 18, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5 has the higher overall point estimate 48.96 to 33.19. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 89.4 for GPT-5 and 41.4 for Mistral Large 3.
- The biggest single benchmark swing is LiveCodeBench (Vals) in Coding, with scores of 85.9% and 55.3%.
- Mistral Large 3 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | GPT-5 | Mistral Large 3 |
|----------|----------|----------|
| Creator | OpenAI | Mistral |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 128K | 128K |
| Overall Score | 48.96 | 33.19 |
| Benchmarks Covered | 6 | 4 |
| Pricing (input/output) | $1.25 / $10.00 | $0.50 / $1.50 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GPT-5 public-lane score: Coming soon
- Mistral Large 3 public-lane score: 20.6 (Estimated · #123/138)

| Benchmark | GPT-5 | Mistral Large 3 | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 8.5% | Coming soon | Coming soon |

### Coding

- Winner: Directional only
- GPT-5 public-lane score: 36.7 (Estimated · #85/160)
- Mistral Large 3 public-lane score: 15.6 (Supported · #141/160)

| Benchmark | GPT-5 | Mistral Large 3 | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 20.09% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.9% | 55.3% | GPT-5 |
| SWE-bench (Vals) | 69.0% | 41.4% | GPT-5 |

### Reasoning

- Winner: Directional only
- GPT-5 public-lane score: 43.7 (Estimated · #75/159)
- Mistral Large 3 public-lane score: 25.7 (Estimated · #133/159)

### Knowledge

- Winner: GPT-5
- GPT-5 public-lane score: 53.1 (Supported · #67/179)
- Mistral Large 3 public-lane score: 32.4 (Supported · #141/179)

| Benchmark | GPT-5 | Mistral Large 3 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 85.6% | 68.4% | GPT-5 |
| MMLU-Pro (Vals) | 86.5% | 79.8% | GPT-5 |

### Instruction Following

- Winner: Directional only
- GPT-5 public-lane score: 89.4 (#35/157)
- Mistral Large 3 public-lane score: 41.4 (#122/157)

## FAQ

### Which is better overall, GPT-5 or Mistral Large 3?

GPT-5 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GPT-5 and Mistral Large 3?

The widest category gap is in instruction following, where the averages are 89.4 for GPT-5 and 41.4 for Mistral Large 3.

### How many benchmarks does GPT-5 cover on BenchLM?

GPT-5 currently has 6 sourced benchmark scores on BenchLM.

### How many benchmarks does Mistral Large 3 cover on BenchLM?

Mistral Large 3 currently has 4 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5 vs GPT-5 mini](/compare/gpt-5-vs-gpt-5-mini)
- [Mistral Large 3 vs GPT-5 mini](/compare/gpt-5-mini-vs-mistral-large-3)
- [GPT-5 vs GPT-5 nano](/compare/gpt-5-vs-gpt-5-nano)
- [Mistral Large 3 vs GPT-5 nano](/compare/gpt-5-nano-vs-mistral-large-3)

## Explore More

- [GPT-5 profile](/models/gpt-5)
- [Mistral Large 3 profile](/models/mistral-large-3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
